Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Training Time”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 199 records · Page 11
All sourcesNASA NTRSDOE OSTI
DOE OSTI2025

Hierarchical Bayesian Modeling for Cosmology: Can NPE reliably replace MCMC?

Hierarchical neural posterior estimation has its place Hierarchical Bayesian Modeling (HBM) combined with MCMC algorithms has been shown to provide more robust and accurate inference for real-world phenomena in which nature takes a nested form. However, MCMC-based inference can be computationally expensive, and its performance often suffers for complex posterior geometries. These costs are especially pertinent for HBM. Studies have recently demonstrated the potential for a flexible, expressive, and amortized hierarchical neural posterior estimator (HNPE) built on Normalizing Flows. These studies have mostly been performed on simple datasets, or they focus on a single parameter from each level of the hierarchy. A systematic study analyzing how both hierarchical methods compare for more complex and realistic datasets is necessary before applying HNPE for scientific measurements. Here, we re-explore the theory behind HNPE and conduct comparative numerical experiments of HNPE and MCMC-based HBM methods on real and synthetic data, including strong gravitational lensing simulations. In particular, we use a suite of diagnostics to show trade-offs in terms of accuracy, precision, time to train or sample, reproducibility, and the need for expert domain knowledge. Especially for higher dimensional and complex posteriors, HNPE is expected to drastically improve on time for inference, accuracy, and precision with an upfront training time cost.

Hur, Rachel [Chicago U.] (ORCID:000900089890445X)↗
NASA NTRS1973

Reaction time to changes in the tempo of acoustic pulse trains.

Investigation of the ability of human observers to detect accelerations and decelerations in the rate of presentation of pulsed stimuli, i.e., changes in the tempo of acoustic pulse trains. Response times to accelerations in tempo were faster than to decelerations. Overall speed of response was inversely related to the pulse repetition rate.

Smith, R. P.↗
DOE OSTI2021

On the feasibility of using physics-informed machine learning for underground reservoir pressure management

In this work, we evaluate the feasibility of using physics-informed machine learning (PIML) for underground energy-related pressure management. To this end, we develop a PIML framework to manage underground reservoir pressures by training neural networks to determine fluid extraction rates for dedicated extraction wells during fluid injection operations given a range of reservoir conditions (e.g., transmissivity and storativity). We implement an automatically-differentiable analytical physics model of fluid flow in porous media within the PIML framework as a proxy for more complicated models. This allows us to execute a sufficient number of training scenarios to fully evaluate the feasibility of using PIML to support pressure management activities. We quantify the number of physics-model parameters required for automatic differentiation to become more efficient than finite-difference gradient calculations. We use a simple scenario with a single injector, extractor, and critical location for our feasibility analysis. We evaluate the effect of the size of the training dataset (i.e., the number of reservoir condition samples) on the accuracy and efficiency of the PIML framework. For an equivalent number of model evaluations, the larger training dataset took less time to train and produced a neural network that was able to more accurately manage reservoir pressures. We also evaluate the effect of the training dataset batch size (i.e., number of reservoir condition samples used to update the neural network coefficients during training; i.e., how the training dataset is partitioned). While training ran faster with larger batch sizes, they produced neural networks that managed pressures less accurately. We demonstrate the approach on a more complex scenario involving 10 injectors, 10 extractors, and 4 critical locations (a relatively high well density of 20 wells/km2). We provide the number of forward and adjoint model evaluations required in each case as an indication of the feasibility of using PIML for pressure management when more complicated physics models with longer execution times are used.

54 ENVIRONMENTAL SCIENCES↗
NASA NTRS2010

Confidence-Based Feature Acquisition

Confidence-based Feature Acquisition (CFA) is a novel, supervised learning method for acquiring missing feature values when there is missing data at both training (learning) and test (deployment) time. To train a machine learning classifier, data is encoded with a series of input features describing each item. In some applications, the training data may have missing values for some of the features, which can be acquired at a given cost. A relevant JPL example is that of the Mars rover exploration in which the features are obtained from a variety of different instruments, with different power consumption and integration time costs. The challenge is to decide which features will lead to increased classification performance and are therefore worth acquiring (paying the cost). To solve this problem, CFA, which is made up of two algorithms (CFA-train and CFA-predict), has been designed to greedily minimize total acquisition cost (during training and testing) while aiming for a specific accuracy level (specified as a confidence threshold). With this method, it is assumed that there is a nonempty subset of features that are free; that is, every instance in the data set includes these features initially for zero cost. It is also assumed that the feature acquisition (FA) cost associated with each feature is known in advance, and that the FA cost for a given feature is the same for all instances. Finally, CFA requires that the base-level classifiers produce not only a classification, but also a confidence (or posterior probability).

Wagstaff, Kiri L.↗
NASA NTRS2009

A Lunar Surface System Supportability Technology Development Roadmap

This paper discusses the establishment of a Supportability Technology Development Roadmap as a guide for developing capabilities intended to allow NASA's Constellation program to enable a supportable, sustainable and affordable exploration of the Moon and Mars. Presented is a discussion of "supportability", in terms of space facility maintenance, repair and related logistics and a comparison of how lunar outpost supportability differs from the International Space Station. Supportability lessons learned from NASA and Department of Defense experience and their impact on a future lunar outpost is discussed. A supportability concept for future missions to the Moon and Mars that involves a transition from a highly logistics dependent to a logistically independent operation is discussed. Lunar outpost supportability capability needs are summarized and a supportability technology development strategy is established. The resulting Lunar Surface Systems Supportability Strategy defines general criteria that will be used to select technologies that will enable future flight crews to act effectively to respond to problems and exploit opportunities in a environment of extreme resource scarcity and isolation. This strategy also introduces the concept of exploiting flight hardware as a supportability resource. The technology roadmap involves development of three mutually supporting technology categories, Diagnostics Test & Verification, Maintenance & Repair, and Scavenging & Recycling. The technology roadmap establishes two distinct technology types, "Embedded" and "Process" technologies, with different implementation and thus different criteria and development approaches. The supportability technology roadmap addresses the technology readiness level, and estimated development schedule for technology groups that includes down-selection decision gates that correlate with the lunar program milestones. The resulting supportability technology roadmap is intended to develop a set of technologies with widest possible capability and utility with a minimum impact on crew time and training and remain within the time and cost constraints of the Constellation program

Oeftering, Richard C.↗
NASA NTRS2011

A Lunar Surface System Supportability Technology Development Roadmap

This paper discusses the establishment of a Supportability Technology Development Roadmap as a guide for developing capabilities intended to allow NASA s Constellation program to enable a supportable, sustainable and affordable exploration of the Moon and Mars. Presented is a discussion of supportability, in terms of space facility maintenance, repair and related logistics and a comparison of how lunar outpost supportability differs from the International Space Station. Supportability lessons learned from NASA and Department of Defense experience and their impact on a future lunar outpost is discussed. A supportability concept for future missions to the Moon and Mars that involves a transition from a highly logistics dependent to a logistically independent operation is discussed. Lunar outpost supportability capability needs are summarized and a supportability technology development strategy is established. The resulting Lunar Surface Systems Supportability Strategy defines general criteria that will be used to select technologies that will enable future flight crews to act effectively to respond to problems and exploit opportunities in an environment of extreme resource scarcity and isolation. This strategy also introduces the concept of exploiting flight hardware as a supportability resource. The technology roadmap involves development of three mutually supporting technology categories, Diagnostics Test and Verification, Maintenance and Repair, and Scavenging and Recycling. The technology roadmap establishes two distinct technology types, "Embedded" and "Process" technologies, with different implementation and thus different criteria and development approaches. The supportability technology roadmap addresses the technology readiness level, and estimated development schedule for technology groups that includes down-selection decision gates that correlate with the lunar program milestones. The resulting supportability technology roadmap is intended to develop a set of technologies with widest possible capability and utility with a minimum impact on crew time and training and remain within the time and cost constraints of the Constellation program.

Oeftering, Richard C.↗
NASA NTRS2011

Lunar Surface Systems Supportability Technology Development Roadmap

The Lunar Surface Systems Supportability Technology Development Roadmap is a guide for developing the technologies needed to enable the supportable, sustainable, and affordable exploration of the Moon and other destinations beyond Earth. Supportability is defined in terms of space maintenance, repair, and related logistics. This report considers the supportability lessons learned from NASA and the Department of Defense. Lunar Outpost supportability needs are summarized, and a supportability technology strategy is established to make the transition from high logistics dependence to logistics independence. This strategy will enable flight crews to act effectively to respond to problems and exploit opportunities in an environment of extreme resource scarcity and isolation. The supportability roadmap defines the general technology selection criteria. Technologies are organized into three categories: diagnostics, test, and verification; maintenance and repair; and scavenge and recycle. Furthermore, "embedded technologies" and "process technologies" are used to designate distinct technology types with different development cycles. The roadmap examines the current technology readiness level and lays out a four-phase incremental development schedule with selection decision gates. The supportability technology roadmap is intended to develop technologies with the widest possible capability and utility while minimizing the impact on crew time and training and remaining within the time and cost constraints of the program.

Oeftering, Richard C.↗
DOE OSTI2024

Efficient distributed continual learning for steering experiments in real-time

Deep learning has emerged as a powerful method for extracting valuable information from large volumes of data. However, when new training data arrives continuously (i.e., is not fully available from the beginning), incremental training suffers from catastrophic forgetting (i.e., new patterns are reinforced at the expense of previously acquired knowledge). Training from scratch each time new training data becomes available would result in extremely long training times and massive data accumulation. Rehearsal-based continual learning has shown promise for addressing the catastrophic forgetting challenge, but research to date has not addressed performance and scalability. To fill this gap, we propose an approach based on a distributed rehearsal buffer that efficiently complements data-parallel training on multiple GPUs to achieve high accuracy, short runtime, and scalability. It leverages a set of buffers (local to each GPU) and uses several asynchronous techniques for updating these local buffers in an embarrassingly parallel fashion, all while handling the communication overheads necessary to augment input minibatches using unbiased, global sampling. We further propose a generalization of rehearsal buffers to support both classification and generative learning tasks, as well as more advanced rehearsal strategies (notably Dark Experience Replay, leveraging knowledge distillation). We illustrate this approach with a real-life HPC streaming application from the domain of ptychographic image reconstruction. Furthermore, we run extensive experiments on up to 128 GPUs of the ThetaGPU supercomputer to compare our approach with baselines representative of training-from-scratch (the upper bound in terms of accuracy) and incremental training (the lower bound). Results show that rehearsal-based continual learning achieves a top-5 validation accuracy close to the upper bound, while simultaneously exhibiting a runtime close to the lower bound.

Asynchronous data management↗
NASA NTRS2001

On-Board Training for US Payloads

The International Space Station (ISS) crew follows a training rotation schedule that puts them in the United States about every three months for a three-month training window. While in the US, the crew receives training on both ISS systems and payloads. Crew time is limited, and system training takes priority over payload training. For most flights, there is sufficient time to train all systems and payloads. As more payloads are flown, training time becomes a more precious resource. Less training time requires payload developers (PDs) to develop alternatives to traditional ground training. To ensure their payloads have sufficient training to achieve their scientific goals, some PDs have developed on-board trainers (OBTs). These OBTs are used to train the crew when no or limited ground time is available. These lessons are also available on-orbit to refresh the crew about their ground training, if it was available. There are many types of OBT media, such as on-board computer based training (OCBT), video/photo lessons, or hardware simulators. The On-Board Training Working Group (OBTWG) and Courseware Development Working Group (CDWG) are responsible for developing the requirements for the different types of media.

Murphy, Benjamin↗
DOE OSTI2026

Rank-Limiting Strategies for Optimizing Tensor-Train Finite-Difference Time-Domain Simulations

We introduce rank-limiting strategies to optimize tensor-train decompositions for three-dimensional finite-difference time-domain simulations using the relationship between the tensors and their specific dimensionality. These include the use of hard caps on the inner ranks of the tensor train decomposition and the use of a group rounding algorithm taking into account all field components simultaneously. Here, several numerical examples are considered to verify the efficacy of the proposed optimization strategies.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2022

Machine Learning Prediction of the Critical Cooling Rate for Metallic Glasses from Expanded Datasets and Elemental Features

In this study, we use a random forest (RF) model to predict the critical cooling rate (R C ) for glass formation of various alloys from features of their constituent elements. The RF model was trained on a database that integrates multiple sources of direct and indirect R C data for metallic glasses to expand the directly measured R C database of less than 100 values to a training set of over 2000 values. The model error on 5-fold cross-validation (CV) is 0.66 orders of magnitude in K/s. The error on leave-out-one-group CV on alloy system groups is 0.59 log units in K/s when the target alloy constituents appear more than 500 times in training data. Using this model, we make predictions for the set of compositions with melt-spun glasses in the database and for the full set of quaternary alloys that have constituents which appear more than 500 times in training data. These predictions identify a number of potential new bulk metallic glass systems for future study, but the model is most useful for the identification of alloy systems likely to contain good glass formers rather than detailed discovery of bulk glass composition regions within known glassy systems.

36 MATERIALS SCIENCE↗
NASA NTRS2009

Performance Support Tools for Space Medical Operations

The early Constellation space missions are expected to have medical capabilities very similar to those currently on the Space Shuttle and International Space Station (ISS). For Crew Exploration Vehicle (CEV) missions to ISS, medical equipment will be located on ISS, and carried into CEV in the event of an emergency. Flight Surgeons (FS) on the ground in Mission Control will be expected to direct the Crew Medical Officer (CMO) during medical situations. If there is a loss of signal and the crew is unable to communicate with the ground, a CMO would be expected to carry out medical procedures without the aid of a FS. In these situations, performance support tools can be used to reduce errors and time to perform emergency medical tasks. Human factors personnel at Johnson Space Center have recently investigated medical performance support tools for CMOs on-orbit, and FSs on the ground. This area of research involved the feasibility of Just-in-time (JIT) training techniques and concepts for real-time medical procedures. In Phase 1, preliminary feasibility data was gathered for two types of prototype display technologies: a hand-held PDA, and a Head Mounted Display (HMD). The PDA and HMD were compared while performing a simulated medical procedure using ISS flight-like medical equipment. Based on the outcome of Phase 1, including data on user preferences, further testing was completed using the PDA only. Phase 2 explored a wrist-mounted PDA, and compared it to a paper cue card. For each phase, time to complete procedures, errors, and user satisfaction were captured. Information needed by the FS during ISS mission support, especially for an emergency situation (e.g. fire onboard ISS), may be located in many different places around the FS s console. A performance support tool prototype is being developed to address this issue by bringing all of the relevant information together in one place. The tool is designed to include procedures and other information needed by a FS during an emergency, as well as procedures and information to be used after the emergency is resolved. Several walkthroughs of the prototype with FSs have been completed within a mockup of an ISS FS console. Feedback on the current tool design as well as recommendations for existing ISS FS displays were captured.

Byrne, Vicky E.↗
DOE OSTI2026

Forest aboveground biomass estimation through integration of sentinel-2 and PALSAR-2 time series: assessing models trained on GEDI and field inventory benchmarks

Accurate and spatially explicit forest Aboveground Biomass (AGB) mapping through remote sensing is critical for quantifying terrestrial carbon stocks and informing effective forest management strategies. However, AGB estimation in dense forests with complex terrain remains challenging due to satellite sensor signal saturation problem (saturation issue occurs in high biomass forests), structural complexity, and limited ground truth for calibration. This study presents a novel framework that integrates multi-temporal Sentinel-2 optical imagery, ALOS PALSAR-2 Synthetic Aperture Radar (SAR) data, and topographic variables with explainable Machine Learning to map AGB across mountainous forests within subtropical and temperate oceanic climate zones of Mexico. We evaluate the effects of temporal granularity and sensor synergy by comparing multiple temporal inputs and sensor configurations (Sentinel-2, PALSAR-2, and their fusion), and assess model performance using two reference datasets: NASA GEDI LiDAR-derived biomass and Mexico’s National Forest and Soil Inventory (INFyS). Our results showed that models trained on INFyS consistently outperformed those trained on GEDI, highlighting limitations in GEDI’s reliability in biomass estimates within this study region. Furthermore, the integration of Sentinel-2 and PALSAR-2 provided improved predictions compared to single-sensor models, particularly when combined with temporally explicit yearly statistics. The best-performing model, which was trained on INFyS data, and considered both Sentinel-2 and PALSAR-2 yearly statistics, as well as topographic variables, achieved an R2 of 0.64, RMSE of 51.10 Mg/ha, and relative RMSE (rRMSE) of 58.69%. Explainable ML analysis identified Sentinel-2 spectral indices and topographic features as key predictors, while PALSAR-2 metrics provided complementary information, partially mitigating saturation effects in high-biomass areas. Specifically, integrating both sensors substantially improved AGB estimation in high biomass forest (≥200 Mg/ha), yielding 98% gains over optical-only model, with resulting estimates exceeding GEDI L4B by 29% and ESA-CCI-BIOMASS by 174%. Terrain-stratified analysis indicated close agreement with GEDI in low-slope areas, with increasing divergence as slope steepness increased, while estimates remained consistently higher than ESA-CCI-BIOMASS across all slope classes. The proposed approach advances multi-sensor fusion and temporal feature engineering for AGB mapping using open-access satellite datasets, providing a scalable and reproducible framework for annual biomass monitoring in topographically complex mountainous forests. The resulting 25 m resolution biomass product has the potential to provide spatially detailed information for forest monitoring and may support applications in carbon accounting and forest management.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2022

A Fast and Accurate Transient Stability Assessment Method Based on Deep Learning: WECC Case Study

Transient stability is one of the critical aspects of power system stability assessment. The increasing integration of inverter-based resources and the retirement of conventional synchronous generators result in the decreasing system inertia and growing complexity of system operating conditions. Using a few selected typical operating conditions cannot guarantee system transient stability in all operating conditions, and the time-domain simulation of all operating conditions requires tremendous time and is often infeasible. This paper proposes a more efficient transient stability assessment method based on deep learning. The binary search method is used to determine the critical clearing time (CCT) in creating training databased by time-domain simulation. This method is fast and accurate with 1 ms resolution. The buses whose CCTs are lower than 200 ms are considered critical buses. Buses close to each other are grouped based on their mutual admittance matrix to reduce the search space of the critical buses. This paper also proposes the generator feature normalization based on the physical model. Case study on the reduced 240-bus WECC system model demonstrates that the proposed method can predict CCT accurately and efficiently.

critical clearing time↗
NASA NTRS1993

Neural networks for atmospheric retrievals

We use neural networks to perform retrievals of temperature and water fractions from simulated clear air radiances for the Atmospheric Infrared Sounder (AIRS). Neural networks allow us to make effective use of the large AIRS channel set, and give good performance with noisy input. We retrieve surface temperature, air temperature at 64 distinct pressure levels, and water fractions at 50 distinct pressure levels. Using 728 temperature and surface sensitive channels, the RMS error for temperature retrievals with 0.2K input noise is 1.2K. Using 586 water and temperature sensitive channels, the mean error with 0.2K input noise is 16 percent. Our implementation of backpropagation training for neural networks on the 16,000-processor MasPar MP-1 runs at a rate of 90 million weight updates per second, and allows us to train large networks in a reasonable amount of time. Once trained, the network can be used to perform retrievals quickly on a workstation of moderate power.

Motteler, Howard E.↗
NASA NTRS2005

The Development of Real-Time Physiological Monitoring and Training Software for Remote Applications

Autogenic Feedback Training Exercise (AFTE) is an protocol and technology developed by Dr. Patricia Cowings and her associates at NASA Ames Research Center as a means to facilitate astronaut adaptation to space and exposure to the microgravity. AFTE is a training method which involves teaching subjects to voluntarily control several of their own physiological responses to environmental stressors. As the procedures matured, the training program was expanded to determine if technology developed to facilitate astronaut adaptation to space would be valuable in treating patients suffering from autonomic and vestibular pathologies and symptomatic relief from nausea and/or blood pressure control anomalies such as hypo- or hypertension. The present study, performed in conjunction with Morehouse School of Medicine, Biomedical Engineering at The University of Akron and NASA Ames Research Center has demonstrated that this technology can be successfully applied over vast distances. The specific purpose of this research was to develop a PC based system which could handle processing of twenty channels of acquired physiological data in addition to the necessary duplex communication protocols that would, for example, permit a patient in Atlanta, GA to be trained by a clinician stationed in San Jose, CA. Sixteen channels of physiological data and 20 channels of processed data are included.

Source record↗